Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add gabrielmoreira/agent-skills-mirror --skill long-video-to-shortsgit clone --depth 1 https://github.com/gabrielmoreira/agent-skills-mirrorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/gabrielmoreira/agent-skills-mirror/long-video-to-shorts)<a href="https://agentmods.dev/skills/gabrielmoreira/agent-skills-mirror/long-video-to-shorts"><img src="https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/long-video-to-shorts/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gabrielmoreira/agent-skills-mirror/long-video-to-shorts"><img src="https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/long-video-to-shorts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00073 | $0.00870 |
| Opus 5 | $0.00036 | $0.00435 |
| Sonnet 5 | $0.00015 | $0.00174 |
| Haiku 4.5 | $0.00007 | $0.00087 |
Grade A, and why
long-video-to-shorts scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Long Video to Shorts
Use this workflow when one long source video carries the output. Supporting clips may exist, but the short-form story comes from selecting self-contained moments inside the long source.
This is a OpenChatCut-native workflow. Use the current project, assets, transcript, timeline, and OpenChatCut editing tools. Do not depend on external download, transcription, ffmpeg, or auto-crop pipelines unless the user explicitly asks for an external source that is not already in the project.
Workflow
- Read the project state before editing. Identify the primary long video, duration, language, speakers, current timeline, transcript readiness, visual descriptions, and aspect ratio.
- Confirm that one long source carries the output. If the project is mainly multiple raw clips with no dominant long source, switch to the Multi Clips to Reels workflow.
- Determine only missing constraints that would change the edit: platform, clip count, target duration, audience, style, captions/title text, music, and whether the user wants options or direct creation.
- If more than one missing constraint remains, ask for them in one
<widget>after loadingwidget-forms. Use text fields for open-ended fields like topic, spoken language, audience, or goals; use single/multi choice fields for bounded choices like platform, count, duration, captions, or music. - Use transcript ranges when available. If transcription is unavailable or unreliable, inspect visual/audio content and ask only for missing context that changes selection.
- Scan for moments that can stand alone: clear setup, hook, claim, proof, emotional turn, lesson, conflict, demonstration, or payoff. Read references/short-form-selection.md when scoring or comparing candidates.
- Build a compact candidate plan before heavy editing. For each output include source range, opening hook, why it stands alone, payoff, target duration, platform treatment, and risks.
- If the user gave enough constraints and asked to create directly, proceed after stating the plan. If the source is very long, the request is vague, or the requested count is high, create or preview the first strongest clip before batching the rest.
- Cut on clean word, phrase, action, or beat boundaries. Tighten filler, false starts, repeated attempts, and dead time only when meaning and tone stay intact.
- Package for the target platform: aspect ratio/crop, title text, styled captions, music, light motion graphics, zooms, speed changes, or transitions only when they support the selected moment.
- QA before reporting done: hook in first seconds, clear payoff, standalone clarity, no misleading title, clean boundaries, platform fit, requested count/duration, timeline names, and export readiness.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 49 lines · 73 tokens per session scan A a7c75d4016f2
long-video-to-shorts is a skill published in the GitHub repository gabrielmoreira/agent-skills-mirror (17 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 870 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…